9 accepted papers
Effectively applying Vision-Language Models (VLMs) to Video Question Answering (VideoQA) hinges on selecting a concise yet comprehensive set of frames, as processing entire videos is computationally infeasible. However, current frame selection methods face a critical trade-off: approaches relying on…
The essence of video lies in pixel dynamics: motion, state transitions, and the flow of visual information across frames. Video Large Language Models (LLMs) have rapidly become the dominant paradigm for video understanding in computer vision, sophisticated multimodal reasoning over complex, long-for…
Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and challenging frontier. Current video benchmarks predominantly target general scenarios where perception/recognition is heav…
In this paper, we introduce Motion-Grounded Video Reasoning, a new motionunderstanding task that requires generating visual answers (video segmentationmasks) according to the input question, and hence needs implicit spatiotemporalreasoning and grounding. This task extends existing spatiotemporal gro…
Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative depth between objects in a scene. To address this is…
Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system. However, the scarcity of long videos with detailed captions and precise…
The goal of building a benchmark (suite of datasets) is to provide a unified protocol for fair evaluation and thus facilitate the evolution of a specific area. Nonetheless, we point out that existing protocols of action recognition could yield partial evaluations due to several limitations. To compr…
Transfer learning has been a popular learning paradigm in the deep learning era, especially in annotation-insufficient scenarios. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to have better transferability to downstream tasks.…
Audio-visual learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multi-modal model outperforms its uni-modal count…